The schematic diagram of the iForest algorithm.

<div><p>Anomaly detection is widely used in cold chain logistics (CCL). But, because of the high cost and technical problem, the anomaly detection performance is poor, and the anomaly can not be detected in time, which affects the quality of goods. To solve these problems, the paper pres...

Full description

Saved in:
Bibliographic Details
Main Author: Zhibo Xie (6790775) (author)
Other Authors: Heng Long (157361) (author), Chengyi Ling (20854893) (author), Yingjun Zhou (2350510) (author), Yan Luo (255674) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852022217102065664
author Zhibo Xie (6790775)
author2 Heng Long (157361)
Chengyi Ling (20854893)
Yingjun Zhou (2350510)
Yan Luo (255674)
author2_role author
author
author
author
author_facet Zhibo Xie (6790775)
Heng Long (157361)
Chengyi Ling (20854893)
Yingjun Zhou (2350510)
Yan Luo (255674)
author_role author
dc.creator.none.fl_str_mv Zhibo Xie (6790775)
Heng Long (157361)
Chengyi Ling (20854893)
Yingjun Zhou (2350510)
Yan Luo (255674)
dc.date.none.fl_str_mv 2025-03-10T17:33:28Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0315322.g003
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/The_schematic_diagram_of_the_iForest_algorithm_/28567764
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biochemistry
Developmental Biology
Science Policy
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
cold chain logistics
relation coefficient ρjk
isolated forest algorithm
div >< p
anomaly detection scheme
anomaly detection performance
average f1 score
anomaly detection
performance indicators
new scheme
improved algorithm
f1 </
correlation coefficient
three types
technical problem
slightly longer
sliding window
recall ),
r </
precision ),
paper presents
p </
mathematical model
lof ),
iforest ).
high cost
data stream
data increases
data flow
cross factor
collected data
abnormal events
dc.title.none.fl_str_mv The schematic diagram of the iForest algorithm.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <div><p>Anomaly detection is widely used in cold chain logistics (CCL). But, because of the high cost and technical problem, the anomaly detection performance is poor, and the anomaly can not be detected in time, which affects the quality of goods. To solve these problems, the paper presents a new anomaly detection scheme for CCL. At first, the characteristics of the collected data of CCL are analyzed, the mathematical model of data flow is established, and the sliding window and correlation coefficient are defined. Then the abnormal events in CCL are summarized, and three types of abnormal judgment conditions based on cor-relation coefficient ρjk are deduced. A measurement anomaly detection algorithm based on the improved isolated forest algorithm is proposed. Subsampling and cross factor are designed and used to overcome the shortcomings of the isolated forest algorithm (iForest). Experiments have shown that as the dimensionality of the data increases, the performance indicators of the new scheme, such as <i>P</i> (precision), <i>R</i> (recall), <i>F1</i> score, and AUC (area under the curve), become increasingly superior to commonly used support vector machines (SVM), local outlier factors (LOF), and iForests. Its average <i>P</i> is 0.8784, average <i>R</i> is 0.8731, average F1 score is 0.8639, and average AUC is 0.9064. However, the execution time of the improved algorithm is slightly longer than that of the iForest.</p></div>
eu_rights_str_mv openAccess
id Manara_8a73901dcd23a315d404fcec11d877bb
identifier_str_mv 10.1371/journal.pone.0315322.g003
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/28567764
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling The schematic diagram of the iForest algorithm.Zhibo Xie (6790775)Heng Long (157361)Chengyi Ling (20854893)Yingjun Zhou (2350510)Yan Luo (255674)BiochemistryDevelopmental BiologyScience PolicyBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedChemical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedcold chain logisticsrelation coefficient ρjkisolated forest algorithmdiv >< panomaly detection schemeanomaly detection performanceaverage f1 scoreanomaly detectionperformance indicatorsnew schemeimproved algorithmf1 </correlation coefficientthree typestechnical problemslightly longersliding windowrecall ),r </precision ),paper presentsp </mathematical modellof ),iforest ).high costdata streamdata increasesdata flowcross factorcollected dataabnormal events<div><p>Anomaly detection is widely used in cold chain logistics (CCL). But, because of the high cost and technical problem, the anomaly detection performance is poor, and the anomaly can not be detected in time, which affects the quality of goods. To solve these problems, the paper presents a new anomaly detection scheme for CCL. At first, the characteristics of the collected data of CCL are analyzed, the mathematical model of data flow is established, and the sliding window and correlation coefficient are defined. Then the abnormal events in CCL are summarized, and three types of abnormal judgment conditions based on cor-relation coefficient ρjk are deduced. A measurement anomaly detection algorithm based on the improved isolated forest algorithm is proposed. Subsampling and cross factor are designed and used to overcome the shortcomings of the isolated forest algorithm (iForest). Experiments have shown that as the dimensionality of the data increases, the performance indicators of the new scheme, such as <i>P</i> (precision), <i>R</i> (recall), <i>F1</i> score, and AUC (area under the curve), become increasingly superior to commonly used support vector machines (SVM), local outlier factors (LOF), and iForests. Its average <i>P</i> is 0.8784, average <i>R</i> is 0.8731, average F1 score is 0.8639, and average AUC is 0.9064. However, the execution time of the improved algorithm is slightly longer than that of the iForest.</p></div>2025-03-10T17:33:28ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0315322.g003https://figshare.com/articles/figure/The_schematic_diagram_of_the_iForest_algorithm_/28567764CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/285677642025-03-10T17:33:28Z
spellingShingle The schematic diagram of the iForest algorithm.
Zhibo Xie (6790775)
Biochemistry
Developmental Biology
Science Policy
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
cold chain logistics
relation coefficient ρjk
isolated forest algorithm
div >< p
anomaly detection scheme
anomaly detection performance
average f1 score
anomaly detection
performance indicators
new scheme
improved algorithm
f1 </
correlation coefficient
three types
technical problem
slightly longer
sliding window
recall ),
r </
precision ),
paper presents
p </
mathematical model
lof ),
iforest ).
high cost
data stream
data increases
data flow
cross factor
collected data
abnormal events
status_str publishedVersion
title The schematic diagram of the iForest algorithm.
title_full The schematic diagram of the iForest algorithm.
title_fullStr The schematic diagram of the iForest algorithm.
title_full_unstemmed The schematic diagram of the iForest algorithm.
title_short The schematic diagram of the iForest algorithm.
title_sort The schematic diagram of the iForest algorithm.
topic Biochemistry
Developmental Biology
Science Policy
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
cold chain logistics
relation coefficient ρjk
isolated forest algorithm
div >< p
anomaly detection scheme
anomaly detection performance
average f1 score
anomaly detection
performance indicators
new scheme
improved algorithm
f1 </
correlation coefficient
three types
technical problem
slightly longer
sliding window
recall ),
r </
precision ),
paper presents
p </
mathematical model
lof ),
iforest ).
high cost
data stream
data increases
data flow
cross factor
collected data
abnormal events